Anthill Inside 2019

On infrastructure for AI and ML: from managing training data to data storage, cloud strategy and costs of developing ML models

Generation of Newsletter using Natural Language Generation

Submitted by Rajesh Gudikoti (@ragudiko) on Monday, 10 June 2019


Preview video

Section: Crisp talk Technical level: Beginner Session type: Lecture

Abstract

We will generate event narratives using NLG.
Assume I am part of event (like Anthill Inside). I conducted a session on particular topic (NLG). I make entry into internal tool. Below information are captured in database.

  1. name of the event

  2. type of event

  3. topic

  4. speaker name/s

  5. location where event is held

  6. number of people attended the event

When publishing team asks me to provide narrative of the event/my session, I start creating narratives by typing.
e.g.
We conducted a session on “July 24, 2019” in “Bangalore”. “Rajesh Gudikoti” handled session on “Natural Language Generation”. The number of people attended was “80”. The event was live streamed to 2000 people. Some people showed enthusiasm to know more about implementation and different use cases of NLG.

How about generating event narrative automatically picking the data from database?

Outline

  1. What is NLG?
  2. What are best use cases for NLG
  3. Brief on sample implementation

Speaker bio

I have spent 2 decades in software industry and worked on both applications and products. My experience is in Java, J2EE, BPM AI(Artificial Intelligence) and Data Science. Currently helping startups and enterprise clients to adopt IBM Watson platform. Involved in developing POCs on AI-NLP for clients. I handle technical seminars and workshops on AI, Kubernetes and Data Science. I am also fortunate to be part of panel discussions in IT as well as in Engineering College.

Links

Preview video

https://ibm.webex.com/ibm/ldr.php?RCID=746ef34c0501bf8db0efe293aa966f02

Comments

  • Rajesh Gudikoti (@ragudiko) Proposer 8 days ago

    password for video is 7fTePnpR

Login with Twitter or Google to leave a comment